© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 119807
    Prev
    Next
    INDEX
    Explanations

    detecting absence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Still
    -1.95
    K
    -1.83
     ""));
    -1.82
    E
    -1.81
    </h3>
    -1.70
     république
    -1.70
    O
    -1.68
    ");
    
    -1.65
    "));
    
    -1.64
    鄣
    -1.60
    POSITIVE LOGITS
     option
    1.64
     who
    1.60
     all
    1.58
     detalla
    1.48
    </strong>
    1.48
    ,
    1.45
     This
    1.43
     idea
    1.41
     C
    1.39
     en
    1.35
    Activations Density 0.004%

    No Known Activations